Preparing data
# res2023[1,]
education_order <- c(
"I never completed any formal education",
"Something else",
"Primary/elementary school",
"Secondary school",
"Associate degree",
"Some college/university study without earning a degree",
"Bachelor’s degree",
"Master’s degree",
"Professional degree"
)
library("plotly")
library("dplyr")
library("tidyr")
library("stringr")
library("ggplot2")
res2018raw <- read.csv("./developer_surveys/survey_results_2018.csv", sep = ",", header = TRUE)
# convert salary to numeric
res2018 <- res2018raw %>%
select(FormalEducation, DevType, Salary = ConvertedSalary, SalaryType, Experience = YearsCoding, AdmiredLanguage = LanguageDesireNextYear) %>%
mutate(Salary = as.numeric(Salary)) %>%
select(-SalaryType) %>%
filter(!is.na(Salary) & Salary != 0) %>%
mutate(Education = str_trim(str_extract(FormalEducation, "^[^(]+"))) %>%
mutate(Education = ifelse(Education == "Other doctoral degree", "Professional degree", Education)) %>%
mutate(Education = factor(Education, ordered = TRUE, levels = education_order))
count(res2018)## n
## 1 46860res2023raw <- read.csv("./developer_surveys/survey_results_2023.csv", sep = ",", header = TRUE)
res2023 <- res2023raw %>%
select(EdLevel, DevType, Salary = ConvertedCompYearly, Experience = YearsCode) %>%
mutate(Education = str_trim(str_extract(EdLevel, "^[^(]+"))) %>%
mutate(Education = factor(Education, ordered = TRUE, levels = education_order))How income is distributed based on education and type
education_devtype_salary <- res2018 %>%
filter(!is.na(DevType) & !is.na(Education)) %>%
filter(Education != "I never completed any formal education") %>%
separate_rows(DevType, sep = ";") %>%
group_by(Education, DevType) %>%
summarize(MedSalary = median(Salary))## `summarise()` has grouped output by 'Education'. You can override
## using the `.groups` argument.g <- ggplot(data = education_devtype_salary, aes(x = Education, y = MedSalary, group = DevType, color = DevType)) +
geom_line() +
scale_fill_brewer(palette = "Blues")
ggplotly(g)How experience vs salary
Bar (x - experience) y(salary)
experience_levels <- c(
"0-2", "3-5", "6-8", "9-11",
"12-14", "15-17", "18-20", "21-23",
"24-26", "27-29", "30 or more"
)
discretize_experience <- function(experience) {
experience <- as.numeric(experience)
return(case_when(
experience >= 0 & experience <= 2 ~ "0-2",
experience >= 3 & experience <= 5 ~ "3-5",
experience >= 6 & experience <= 8 ~ "6-8",
experience >= 9 & experience <= 11 ~ "9-11",
experience >= 12 & experience <= 14 ~ "12-14",
experience >= 15 & experience <= 17 ~ "15-17",
experience >= 18 & experience <= 20 ~ "18-20",
experience >= 21 & experience <= 23 ~ "21-23",
experience >= 24 & experience <= 26 ~ "24-26",
experience >= 27 & experience <= 29 ~ "27-29",
TRUE ~ "30 or more"
))
}
exp_sal18 <- res2018 %>%
select(Experience, Salary) %>%
na.omit() %>%
mutate(Experience = gsub(" years", "", Experience)) %>%
mutate(Experience = factor(Experience, levels = experience_levels, ordered = TRUE)) %>%
group_by(Experience) %>%
summarize(MedSalary = median(Salary)) %>%
mutate(year = "2018")
exp_sal18## # A tibble: 11 × 3
## Experience MedSalary year
## <ord> <dbl> <chr>
## 1 0-2 15876 2018
## 2 3-5 30597 2018
## 3 6-8 45283 2018
## 4 9-11 55812 2018
## 5 12-14 67706. 2018
## 6 15-17 77104 2018
## 7 18-20 85000 2018
## 8 21-23 95968 2018
## 9 24-26 96000 2018
## 10 27-29 96626 2018
## 11 30 or more 105253 2018exp_sal23 <- res2023 %>%
select(Experience, Salary) %>%
na.omit() %>%
mutate(Experience = discretize_experience(Experience)) %>%
mutate(Experience = factor(Experience, levels = experience_levels, ordered = TRUE)) %>%
group_by(Experience) %>%
summarize(MedSalary = median(Salary)) %>%
mutate(year = "2023")## Warning: There was 1 warning in `mutate()`.
## ℹ In argument: `Experience = discretize_experience(Experience)`.
## Caused by warning in `discretize_experience()`:
## ! NAs introduced by coercionexp_sal23## # A tibble: 11 × 3
## Experience MedSalary year
## <ord> <dbl> <chr>
## 1 0-2 19276 2023
## 2 3-5 39724 2023
## 3 6-8 53545 2023
## 4 9-11 68276 2023
## 5 12-14 77104 2023
## 6 15-17 83173 2023
## 7 18-20 89222 2023
## 8 21-23 96657 2023
## 9 24-26 105548 2023
## 10 27-29 110000 2023
## 11 30 or more 106000 2023exp_sal <- union(exp_sal18, exp_sal23)
exp_sal## # A tibble: 22 × 3
## Experience MedSalary year
## <ord> <dbl> <chr>
## 1 0-2 15876 2018
## 2 3-5 30597 2018
## 3 6-8 45283 2018
## 4 9-11 55812 2018
## 5 12-14 67706. 2018
## 6 15-17 77104 2018
## 7 18-20 85000 2018
## 8 21-23 95968 2018
## 9 24-26 96000 2018
## 10 27-29 96626 2018
## # ℹ 12 more rows## con
ggplot(exp_sal, aes(x = Experience, y = MedSalary, fill = year, color = year)) +
geom_bar(stat = "identity", position = position_dodge(), width = 0.45)
# facet_wrap(~year)Inflation plot
With inflation
Are admired languages well paid
admired18 <- res2018 %>%
select(AdmiredLanguage, Salary) %>%
separate_rows(AdmiredLanguage, sep = ";") %>%
group_by(AdmiredLanguage) %>%
summarize(SalaryMed = median(Salary), AdmiredLanguageCount = n())
g <- ggplot(admired18, aes(x = AdmiredLanguageCount, y = SalaryMed, color = AdmiredLanguage, fill = AdmiredLanguage)) +
geom_jitter()
ggplotly(g)